t3.py

import asyncio
from playwright.async_api import async_playwright
from jinja2 import Environment, FileSystemLoader
import os
import re

PRODUCT_URLS = [
    "https://www.htgsupply.com/products/digital-greenhouse-hhp-1000w-de-grow-light/#tab-description",
    # add more URLs here if needed
]

env = Environment(loader=FileSystemLoader("."))

def slugify(text):
    return re.sub(r'[\W_]+', '-', text.lower()).strip("-")

async def scrape_product(page, url):
    await page.goto(url, timeout=60000)
    await page.wait_for_selector("h1.product-title", timeout=15000)

    title = await page.locator("h1.product-title").text_content()
    price = await page.locator(".price > span > bdi").first.text_content()
    description_html = await page.locator("div.woocommerce-Tabs-panel--description").inner_html()

    specifications = {}
    spec_items = page.locator(".accordion-item")
    count = await spec_items.count()
    for i in range(count):
        heading = await spec_items.nth(i).locator(".accordion-title").text_content()
        if heading and "spec" in heading.lower():
            rows = spec_items.nth(i).locator("table tr")
            for j in range(await rows.count()):
                th = await rows.nth(j).locator("th").text_content()
                td = await rows.nth(j).locator("td").text_content()
                if th and td:
                    specifications[th.strip()] = td.strip()
            break

    return {
        "title": title.strip() if title else "Untitled",
        "price": price.strip() if price else "N/A",
        "description_html": description_html.strip() if description_html else "",
        "specifications": specifications,
        "url": url,
        "slug": slugify(title or "product")
    }

async def main():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()

        for url in PRODUCT_URLS:
            try:
                data = await scrape_product(page, url)
                template = env.get_template("product_template.html")
                html = template.render(**data)

                output_file = f"output_{data['slug']}.html"
                with open(output_file, "w") as f:
                    f.write(html)
                print(f"[+] Wrote HTML output to: {output_file}")

            except Exception as e:
                print(f"[!] Error scraping {url}: {e}")

        await browser.close()

if __name__ == "__main__":
    asyncio.run(main())